-
公开(公告)号：US10672387B2
公开(公告)日：2020-06-02
申请号：US15839499
申请日：2017-12-12
Applicant: GOOGLE LLC
Inventor： Richard Lyon , Christopher Hughes , Yuxuan Wang , Ryan Rifkin , Pascal Getreuer
Abstract: The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.
-
2.发明授权公开(公告)号：US11984117B2
公开(公告)日：2024-05-14
申请号：US17886726
申请日：2022-08-12
Applicant: Google LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
IPC: G10L15/20 , G10L15/02 , G10L15/08 , G10L15/22 , G10L21/0232 , G10L25/84 , G10L21/0216
CPC classification number: G10L15/20 , G10L15/02 , G10L15/08 , G10L15/22 , G10L21/0232 , G10L25/84 , G10L2015/025 , G10L2015/088 , G10L2015/223 , G10L2021/02166
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
3.发明授权公开(公告)号：US11417324B2
公开(公告)日：2022-08-16
申请号：US16886139
申请日：2020-05-28
Applicant: Google LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
IPC: G10L15/20 , G10L15/02 , G10L15/08 , G10L15/22 , G10L21/0232 , G10L25/84 , G10L21/0216
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
4.发明公开公开(公告)号：US20240304187A1
公开(公告)日：2024-09-12
申请号：US18662334
申请日：2024-05-13
Applicant: GOOGLE LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
IPC: G10L15/20 , G10L15/02 , G10L15/08 , G10L15/22 , G10L21/0216 , G10L21/0232 , G10L25/84
CPC classification number: G10L15/20 , G10L15/02 , G10L15/08 , G10L15/22 , G10L21/0232 , G10L25/84 , G10L2015/025 , G10L2015/088 , G10L2015/223 , G10L2021/02166
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
5.发明授权公开(公告)号：US10706842B2
公开(公告)日：2020-07-07
申请号：US16609619
申请日：2019-01-14
Applicant: Google LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
IPC: G10L15/20 , G10L15/02 , G10L15/08 , G10L15/22 , G10L21/0232 , G10L25/84 , G10L21/0216
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. Various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20200066263A1
公开(公告)日：2020-02-27
申请号：US16609619
申请日：2019-01-14
Applicant: Google LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
7.发明授权公开(公告)号：US12260857B2
公开(公告)日：2025-03-25
申请号：US18662334
申请日：2024-05-13
Applicant: GOOGLE LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
IPC: G10L15/22 , G10L15/02 , G10L15/08 , G10L15/20 , G10L21/0232 , G10L25/84 , G10L21/0216
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
8.发明申请公开(公告)号：US20220392441A1
公开(公告)日：2022-12-08
申请号：US17886726
申请日：2022-08-12
Applicant: Google LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
9.发明申请公开(公告)号：US20200294496A1
公开(公告)日：2020-09-17
申请号：US16886139
申请日：2020-05-28
Applicant: Google LLC
Inventor： Christopher Hughes , Yiteng Huang , Turaj Zakizadeh Shabestary , Taylor Applebaum
Abstract: Techniques are described for selectively adapting and/or selectively utilizing a noise reduction technique in detection of one or more features of a stream of audio data frames. For example, various techniques are directed to selectively adapting and/or utilizing a noise reduction technique in detection of an invocation phrase in a stream of audio data frames, detection of voice characteristics in a stream of audio data frames (e.g., for speaker identification), etc. Utilization of described techniques can result in more robust and/or more accurate detections of features of a stream of audio data frames in various situations, such as in environments with strong background noise. In various implementations, described techniques are implemented in combination with an automated assistant, and feature(s) detected utilizing techniques described herein are utilized to adapt the functionality of the automated assistant.
-
公开(公告)号：US20180197533A1
公开(公告)日：2018-07-12
申请号：US15839499
申请日：2017-12-12
Applicant: GOOGLE LLC
Inventor： Richard Lyon , Christopher Hughes , Yuxuan Wang , Ryan Rifkin , Pascal Getreuer
Abstract: The various implementations described herein include methods, devices, and systems for recognizing speech, such as user commands. In one aspect, a method includes: (1) receiving audio input data via the one or more microphones; (2) generating a plurality of energy channels for the audio input data; (3) generating a feature vector by performing a per-channel normalization to each channel of the plurality of energy channels; and (4) obtaining recognized speech from the audio input utilizing the feature vector.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.013 seconds)
